Nilesh Ahuja | Search arXiv

arXiv2026

CURA: Certified Runtime Alarms for Computer-Use Agents

Self-report is the cheapest oversight channel a deployer has, and on capable computer-use agents (CUAs) it fails precisely where oversight matters. On 361 OSWorld tasks our pipeline, a read-only feasibility gate, a planner, and a GUI executor, reaches a mean task score of 82.9, above the 72.4 human reference, yet 64 of its 71 failures (90%) end with a success claim, 61 acknowledging no blocker, and the explicit failure affordance is never used in roughly 9,100 calls. We introduce CURA (Certified Runtime Alarms for Computer-Use Agents), an external monitor that reads only harness-visible telemetry, with no model internals, extra LLM calls, or prompt changes, and turns the running trajectory into a sequential test with certified false-alarm control. At alpha = 0.10 its CUSUM alarm detects 42.3% of failures a median of 31 steps before termination at a realized false-alarm rate of 0.066, and risk is partly resolvable before the first action (gate probe, 0.69 AUROC). Retrospectively the composite reaches 0.828 AUROC (fold-internal floor 0.802), but its margin over a total-token baseline is not significant (Delta = +0.026, p = 0.101); the separation is online, where CURA recalls more at matched certified budgets: 0.41 versus 0.34 at alpha = 0.10, 0.56 versus 0.38 at alpha = 0.20. Alarm-gated mid-execution oversight recovers 23 of 70 failures while spending a frontier overseer on 38, giving a deployable cascade at mean score 86.8 and 84.5% full-solve (305 of 361). The certificate bounds false alarms only. We also report where behavioral monitoring is uninformative.

cs.AI↗

arXiv2026

From Generation to Discovery: Diffusion Mutation Kernels for Circuit and Physical Design

Generation and discovery are different problems. A generative model trained on valid artifacts reproduces a distribution, whereas discovery must produce artifacts that lie outside the observed corpus, satisfy hard structural constraints, and improve on established designs under evaluation that the model cannot influence. We introduce a diffusion-based discovery framework. Unlike conventional generative models that sample from learned distributions, it learns transition operators that transform existing artifacts into new candidates. Controlled partial re-noising followed by denoising defines a diffusion mutation kernel, a learned transition distribution that preserves the structural regularities of feasible designs while moving between regions of the design space. The learned model supplies feasibility structure only, and all correctness and performance judgments remain with external engineering tools. Intermediate diffusion trajectories are additionally monitored under a conformal risk budget so that unpromising candidates are discarded before expensive evaluation. We evaluate the framework on three electronic design spaces, an environment that supplies rigorous non-differentiable evaluators in the form of simulation, formal equivalence checking, and industrial physical implementation. The framework discovers 32-bit prefix adders that are formally verified equivalent to addition over all 2^64 input pairs and reduce delay by 17% and area by 18% relative to Kogge-Stone under a placed-and-timed flow; seven independently re-simulated amplifier topologies absent from the training corpus, spanning gains of 21.9-66.1 dB and bandwidths of 72.9 kHz-207 MHz; and macro placements on held-out netlists reaching 0.68x wirelength of an industrial placer.

eess.SY↗